Vectorize markdown textbook chapters and manage Qdrant Cloud collections.
npx skills add https://github.com/FAIQahm/hackathon_I_book --skill qdrant-manager
Please help me install this Agent Skill. Skill: qdrant-manager Source: https://github.com/FAIQahm/hackathon_I_book/tree/main/.claude/skills/qdrant-manager Command: npx skills add https://github.com/FAIQahm/hackathon_I_book --skill qdrant-manager
This skill centralizes the process of vectorizing textbook chapters and managing Qdrant Cloud collections to enable fast, retrieval-augmented generation across large markdown datasets.
Initialize and vectorize your chapters by running the setup script to create the collection and index docs for RAG.
High-intent search queries and answers about installing and using this skill.
Vectorizing markdown for RAG involves header-based chunking and language-aware metadata tagging, which this skill automates to populate Qdrant Cloud collections with searchable content.
Yes, it supports language-aware metadata tagging for multilingual markdown sources, enabling filtered search across chapters by language within Qdrant Cloud collections.
You need a QDRANT URL and API key plus an embedding model, with configurable inputs for collection name, vector size, and batch settings to manage Qdrant Cloud collections.
Qdrant-backed retrieval works with header-based chunking by splitting markdown content at headers, preserving document structure to ensure coherent and precise search results.
Using Qdrant Cloud centralizes collection management and querying, handling large markdown datasets more efficiently than local storage for retrieval-augmented generation workflows.
ScavieFaeDetect the host platform, install dependencies, and configure Dolphin, Slippi, and Phillip.
patrykkopycinskiSet up a RAG pipeline with Elasticsearch for vector retrieval.
dotlab-hqBuild RAG pipelines that ingest, chunk, embed, and retrieve documents for LLMs.
Prompt-or-Die-LabsDeploy and operate a Qdrant vector database on Railway for semantic search.
